Redesigning Regularization for Effective Policy Smoothing

arXiv:2606.13169 · cs.RO · Submitted 2026-06-11 · Read on arXiv

cs.RO

Submitted: 2026-06-11

Updated: 2026-10-13

Comments: accepted for publication in RA-L

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regularization — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States
• AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning
• Learning Smooth Time-Varying Linear Policies with an Action Jacobian Penalty
• Gymnasium: A Standard Interface for Reinforcement Learning Environments
• Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error
• Flexible Empowerment at Reasoning with Extended Best-of-N Sampling
• RSL-RL: A Learning Library for Robotics Research

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies